AMD Radeon 8040S vs Intel Arc B390 Comparison

FAQ

Q: What are the average benchmark scores for the AMD Radeon 8040S and Intel Arc B390?

A: The AMD Radeon 8040S has an average benchmark score of 2440, while the Intel Arc B390 has an average benchmark score of 1482.

Q: Which GPU has a higher percentile ranking among all GPUs?

A: The AMD Radeon 8040S ranks in the 17th percentile of all GPUs, while the Intel Arc B390 ranks in the 9th percentile.

Q: How do the nearest rivals compare to each GPU?

A: The AMD Radeon 8040S's closest rival is the NVIDIA GeForce 710M with a 0.3% higher average score, while the Intel Arc B390's closest rival is the NVIDIA GeForce GT 520MX with a 1.3% higher average score.

Q: What are the process nodes for each GPU?

A: The AMD Radeon 8040S uses a 4 nm process node from TSMC, while the Intel Arc B390 uses a 3 nm process node from Intel.

Q: What is the TDP of each GPU?

A: The AMD Radeon 8040S has a TDP of 55 W, while the Intel Arc B390 has a TDP of 80 W.

Q: What API support do both GPUs share?

A: Both the AMD Radeon 8040S and Intel Arc B390 support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Architecture Differences

The AMD Radeon 8040S and Intel Arc B390 represent fundamentally different architectural approaches. The AMD part uses the Strix Halo chip with RDNA 3.5 architecture, belonging to the Navi Mobile (RX 8000M) generation. The Intel part uses the Panther Lake chip with Xe3-LPG architecture, belonging to the Arc Graphics-M (Panther Lake) generation. These are not just different implementations of similar ideas; they reflect distinct design philosophies from each manufacturer.

The process node difference is notable. AMD builds the Radeon 8040S on a 4 nm process at TSMC, while Intel builds the Arc B390 on a 3 nm process at Intel. The die size for the AMD part is 308 mm², while the Intel die size is unknown. Transistor counts are unknown for both.

Clock behavior differs significantly. The AMD Radeon 8040S has a base clock of 1295 MHz and a boost clock of 2800 MHz. The Intel Arc B390 has a base clock of 300 MHz and a boost clock of 2500 MHz. The AMD part starts at a much higher base clock, suggesting a more aggressive default operating point, while the Intel part has a very low base clock with a substantial boost range.

Shader configuration is a major divergence. The AMD Radeon 8040S has 1024 shading units, 64 texture mapping units, and 32 render output units. The Intel Arc B390 has 1536 shading units, 48 texture mapping units, and 24 render output units. Intel packs 50% more shading units into a smaller number of TMUs and ROPs. This indicates a different balance between compute throughput and fixed-function rasterization work.

Ray tracing hardware also differs. The AMD part has 16 ray tracing cores, while the Intel part has 12. Neither GPU has tensor cores listed.

The memory subsystem is shared in both cases, with system shared memory, system shared type, system shared bus width, and system dependent bandwidth. Neither GPU has dedicated VRAM, relying entirely on the host system's memory.

Power delivery differs, with the AMD Radeon 8040S rated at 55 W and the Intel Arc B390 rated at 80 W. Both are integrated graphics processors (IGP) with no power connectors and portable device dependent display outputs. The bus interface differs: AMD uses PCIe 5.0 x16, while Intel uses IGP.

The Verdict

The recorded data shows a clear average score advantage for the AMD Radeon 8040S, which posts an average benchmark score of 2440 versus 1482 for the Intel Arc B390. That is a 64.6% higher average score for the AMD part. The percentile rankings reinforce this gap: the AMD Radeon 8040S sits in the 17th percentile of all GPUs, while the Intel Arc B390 sits in the 9th percentile.

The nearest rival data tells a similar story. The AMD Radeon 8040S competes with the NVIDIA GeForce 710M (0.3% higher), Intel HD Graphics 610 (0.6% higher), NVIDIA GeForce GT 710M (0.7% higher), and AMD Radeon RX 7400 (1.1% lower). These are all closely clustered scores, indicating the AMD part is firmly in entry-level territory. The Intel Arc B390's nearest rivals are the NVIDIA GeForce GT 520MX (1.3% higher), NVIDIA GeForce 800M (1.5% higher), NVIDIA GeForce GT 625 OEM (2.5% higher), and NVIDIA GeForce GT 710 (2.7% higher). These rivals are all lower-performing than the AMD part's rivals, confirming the Intel part sits in a lower performance tier.

For users selecting between these two integrated GPUs, the data points to the AMD Radeon 8040S as the stronger performer in overall average score. The Intel Arc B390 does offer higher raw FP32 throughput at 7.680 TFLOPS versus 5.734 TFLOPS, and much higher FP16 throughput at 15.36 TFLOPS versus 5.734 TFLOPS, but the average benchmark score does not reflect an advantage. The AMD part delivers higher pixel rate at 89.60 GPixel/s versus 60.00 GPixel/s, and higher texture rate at 179.2 GTexel/s versus 120.0 GTexel/s.

The power envelope favors AMD as well, with the Radeon 8040S drawing 55 W compared to 80 W for the Arc B390. For integrated graphics in portable devices, this lower power draw is a meaningful distinction.

Specification Differences

| Specification | AMD Radeon 8040S | Intel Arc B390 |

|---|---|---|

| Chip | Strix Halo | Panther Lake |

| Architecture | RDNA 3.5 | Xe3-LPG |

| Generation | Navi Mobile (RX 8000M) | Arc Graphics-M (Panther Lake) |

| Process Node | 4 nm | 3 nm |

| Foundry | TSMC | Intel |

| Die Size | 308 mm² | unknown |

| Base Clock | 1295 MHz | 300 MHz |

| Boost Clock | 2800 MHz | 2500 MHz |

| Shading Units | 1024 | 1536 |

| TMUs | 64 | 48 |

| ROPs | 32 | 24 |

| Ray Tracing Cores | 16 | 12 |

| Pixel Rate | 89.60 GPixel/s | 60.00 GPixel/s |

| Texture Rate | 179.2 GTexel/s | 120.0 GTexel/s |

| FP32 | 5.734 TFLOPS | 7.680 TFLOPS |

| FP16 | 5.734 TFLOPS (1:1) | 15.36 TFLOPS (2:1) |

| TDP | 55 W | 80 W |

| Bus Interface | PCIe 5.0 x16 | IGP |

| Release Date | 2025-01-05 | 2026-01-26 |

| Predecessor | Polaris Mobile | none |

Head-to-Head Benchmarks

The two GPUs share only one common benchmark in the database, and that is the only recorded head-to-head comparison. The Intel Arc B390 has a 3DMark Steel Nomad DX12 score of 1482, which serves as its sole benchmark entry. The AMD Radeon 8040S has no equivalent 3DMark Steel Nomad result recorded.

The AMD Radeon 8040S has a broader benchmark profile with seven recorded tests. Its PassMark DirectX 10 score is 48, DirectX 11 score is 80, DirectX 12 score is 47, DirectX 9 score is 134, G2D score is 1052, G3D score is 10578, and GPU compute score is 5138. The average benchmark score of 2440 is derived from this set.

The Intel Arc B390's average benchmark score of 1482 comes from its single 3DMark Steel Nomad DX12 result. This sparse data makes direct comparison difficult, but the average score is the primary metric in the database, and it shows a substantial gap.

The nearest rival deltas reinforce this gap. The AMD Radeon 8040S's closest rival scores within 0.3% of it, while the Intel Arc B390's closest rival scores within 1.3%. The difference in nearest rival performance levels is stark: the AMD part competes with GPUs scoring around 2433 to 2467, while the Intel part competes with GPUs scoring around 1443 to 1463.

Where Each One Wins

The AMD Radeon 8040S wins on average benchmark score with 2440 versus 1482, a 64.6% advantage. This is the single most important metric in the database for comparing overall performance. The AMD part also wins on pixel rate at 89.60 GPixel/s versus 60.00 GPixel/s, and texture rate at 179.2 GTexel/s versus 120.0 GTexel/s. These rate advantages suggest better rasterization throughput for traditional rendering workloads.

The AMD Radeon 8040S also wins on power efficiency, with a 55 W TDP versus 80 W for the Intel Arc B390. Lower power draw combined with higher average score indicates better performance per watt, a meaningful factor for integrated GPUs in portable devices.

The Intel Arc B390 wins on raw compute specifications. Its FP32 throughput of 7.680 TFLOPS exceeds the AMD part's 5.734 TFLOPS by 34%. The FP16 advantage is much larger: 15.36 TFLOPS versus 5.734 TFLOPS, a 168% difference. The Intel part achieves this FP16 advantage through a 2:1 ratio, while the AMD part operates at a 1:1 ratio for FP16 versus FP32. This suggests the Intel architecture is better suited for workloads that can exploit FP16 arithmetic, such as certain AI inference or mixed-precision compute tasks.

The Intel Arc B390 also wins on shading unit count with 1536 versus 1024, a 50% advantage. This higher shader count does not translate to a higher average benchmark score, but it indicates the Intel part has more parallel compute paths available.

The AMD Radeon 8040S wins on ray tracing core count with 16 versus 12, a 33% advantage. The AMD part also wins on TMU and ROP counts, with 64 versus 48 TMUs and 32 versus 24 ROPs.

The release timeline favors AMD, with a 2025-01-05 release date versus 2026-01-26 for Intel. Both GPUs are currently marked as Active in production status.

For use cases involving traditional 3D rendering, rasterization, and general graphics workloads, the data indicates the AMD Radeon 8040S delivers higher average performance. For compute-heavy workloads that can leverage FP16 arithmetic, the Intel Arc B390's specification sheet suggests an advantage, though no benchmark data confirms this in practice.